© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187466
    Prev
    Next
    INDEX
    Explanations

    vehicles, cars, command, line

    np_acts-logits-general · gemini-2.5-flash-lite

    expressing intent or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     usr
    0.61
     根据
    0.52
    Imagem
    0.51
    Whats
    0.50
     ㅇ
    0.48
     Mirrors
    0.47
     _____________
    0.47
     _______
    0.47
     একান্ত
    0.46
     "_
    0.45
    POSITIVE LOGITS
    大
    0.52
    恣
    0.51
     außen
    0.51
    几十
    0.46
    数十
    0.45
    外し
    0.45
    стки
    0.45
    捕
    0.45
    受
    0.44
    átiles
    0.43
    Activations Density 0.000%

    No Known Activations